Research Article
Gender and Handedness Prediction from Offline Handwriting Using Convolutional Neural Networks
Table 1
Number of training and text lines, per subclass and experiment, from Offline IAM database.
| | Gender | | Male (M) | Female (F) | | Train | Test | Train | Test |
| | 5,228 | 1,659 | 3,234 | 805 |
| | Handedness | | Right-handed (R) | Left-handed (L) | | Train | Test | Train | Test |
| | 6,946 | 3,011 | 728 | 250 |
| | Combined | | RM | LM | RF | LF | | Train | Test | Train | Test | Train | Test | Train | Test |
| | 4,851 | 1,473 | 429 | 134 | 2,497 | 1,113 | 297 | 132 |
|
|